With the 2016 Higher Education Policy Institute report showing a rising problem in students mental health, universities are under increasing pressure to take care of their students wellbeing, as well as their academic success. With thousands of learners on the roll, it’s not easy to keep personal tabs on everyone, but technology can spot the signs that an individual may be in trouble.
Using learning analytics will allow institutions to personalise interventions and uncover hidden patterns in their student data, reflect on how students are interacting, and make evidence-informed decisions about how best to support, or challenge, their students.
Imagine a student has not accessed the virtual learning environment, been to the library or engaged in the college community for a number of weeks and has missed their last couple of deadlines. Data about all of this is already being collected (although it’s often geared toward internal admin needs) and can be used to ring an alarm bell.
Proof that a student is not engaging as expected, or whose habits have changed, may indicate a personal problem – one that a timely human intervention by a tutor could mitigate. This could prevent a student from dropping out of his or her course, or worse, developing a serious mental health problem.
Using learning analytics will allow institutions to personalise interventions and uncover hidden patterns in their student data
Analytics data can also be rolled into a predictive model of student success or failure. For example, a model at the New York Institute of Technology successfully identified 74 per cent of students who subsequently dropped out as having been ‘at risk’. Could some of these drop-outs have been prevented if an appropriate intervention had been staged? My feeling is yes. I also believe any education institution – which states that student success and wellbeing is core to its mission – has a clear moral obligation to actively pool and analyse data for the benefit of students as part of their duty of care.
There is growing evidence that learning analytics, while helping all students, is particularly effective for disadvantaged groups, who are more likely to drop out. Students from disadvantaged backgrounds who run into problems at university may lack social capital or confidence to seek help, and are less likely to have a family support network with experience of universities. Such students may be particularly reliant on fast referral to existing university pastoral care. Learning analytics can provide a rapid path through to such care, rather like an NHS patient being preferred straight to a consultant as necessary.
Research also shows that learning analytics have a positive effect on retention rates and student wellbeing. We can give three examples:
- When learning analytics were applied at Columbus State University College in the US, retention rose by 4.2 per cent overall, but 5.7 per cent for low-income students.
- In Australia, a three-phase scheme at the University of New England saw drop-out rates fall from 18 to 12 per cent. The project encouraged peer-to-peer student networking, dissemination of information and, via a daily email alert, connected support staff with the students on a daily basis. Feedback from students showed that it was successful in increasing their sense of belonging to a community, and sharing their experiences of study, thus increasing their motivation.
- Salford College describe learning analytics as a “vital tool” in pointing to students whose personal circumstances made studying extremely challenging. For example, the college was able to provide extra support to two struggling students. Both had poor attendance records, but their digital footprint showed they were tending to study online late at night and in the early hours. It turned out that one had suffered a family bereavement, while the other was dealing with hospital appointments and child care issues.
Student accommodation developer Unite Students has also recognised the role that data collection and learning analytics could play in creating what it calls The Resilient Student.
The union’s report, Student Resilience (May 2017), says: ”At a time when between 12 per cent (Unite Students, 2016) and 20 per cent (NUS, 2013) of students report having a mental health problem and a staggering 92 per cent identify as having experienced mental distress, the importance of cultivating resilience amongst learners of all ages must be both recognised and acted upon.
“There is an opportunity to link the development of student engagement and learning analytics with the resilience agenda so as to ensure that there are ways of capturing data associated with the development of resilient characteristics.”
Although some may argue such data collection is a bit too Big Brother, students broadly welcome the idea, as a Jisc survey* conducted among students (March 2017) shows. The vast majority (82%) of respondents would be happy to have their learning data collected if it improved their grades, and 61% would be happy to have their learning data collected if it stopped them from dropping out. It’s important to point out, however, that making interventions with students on the basis of the analytics will require their explicit consent. Following successful trials, a learning analytics app is due to be launched by Jisc in September, which gives students control over interventions. The app is part of a wider Jisc project to create a learning analytics service for the education sector.
*The youthsight survey commissioned by Jisc questioned 1000 16 to 24-year-olds.
Jisc is the UK higher, further education and skills sectors’ not-for-profit organisation for digital services and solutions. We:
- operate shared digital infrastructure and services
- negotiate sector-wide deals with IT vendors and commercial publishers and
- provide trusted advice and practical assistance for universities, colleges and learning providers.
For more information, contact the press team: firstname.lastname@example.org